Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special characters and identifiers, like symbols and codes

    oai_token-act-pair · gpt-3.5-turbo

    special characters and references to specific plant species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    espie
    -0.77
     Prol
    -0.76
     CPS
    -0.75
     externalToEVAOnly
    -0.72
     Ivy
    -0.71
     Tinker
    -0.70
     Feder
    -0.70
    ITED
    -0.70
     Kathleen
    -0.70
     Jenner
    -0.70
    POSITIVE LOGITS
    á
    1.50
    ĵĺ
    1.30
    ´
    1.16
    ĥ
    1.15
    á½
    1.13
     á
    1.12
    ¼
    1.10
    ¸
    1.09
    ½
    1.07
    IJ
    1.05
    Act Density 0.005%

    No Known Activations